Multi-object multi-part scene segmentation is a challenging task whose complexity scales exponentially with part granularity and number of scene objects. To address the task, we propose a plug-and-play approach termed OLAF. First, we augment the input (RGB) with channels containing object-based structural cues (fg/bg mask, boundary edge mask). We propose a weight adaptation technique which enables regular (RGB) pre-trained models to process the augmented (5-channel) input in a stable manner during optimization. In addition, we introduce an encoder module termed LDF to provide low-level dense feature guidance. This assists segmentation, particularly for smaller parts. OLAF enables significant mIoU gains of 3.3 (Pascal-Parts-58), 3.5 (Pascal-Parts-108) over the SOTA model. On the most challenging variant (Pascal-Parts-201), the gain is 4.0. Experimentally, we show that OLAF's broad applicability enables gains across multiple architectures (CNN, U-Net, Transformer) and datasets. The code is available at olafseg.github.io
@article{arxiv.2411.02858,
title = {OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing},
author = {Pranav Gupta and Rishubh Singh and Pradeep Shenoy and Ravikiran Sarvadevabhatla},
journal= {arXiv preprint arXiv:2411.02858},
year = {2024}
}
Comments
Accepted in The European Conference on Computer Vision (ECCV) 2024